Explainable Machine Learning untuk Mengidentifikasi Determinan Kerugian Pascabencana Banjir dan Longsor di Sumatera Barat
Article Sidebar
Main Article Content
Abstract
Bencana banjir dan longsor menyebabkan kerusakan fisik serta kerugian ekonomi yang signifikan pada sektor permukiman. Identifikasi faktor-faktor yang memengaruhi besarnya kerugian pascabencana menjadi penting untuk mendukung perencanaan rehabilitasi dan rekonstruksi yang lebih efektif. Penelitian ini bertujuan mengembangkan model Explainable Machine Learning untuk mengidentifikasi determinan utama kerugian pascabencana banjir dan longsor di Provinsi Sumatera Barat. Dataset yang digunakan berasal dari data Damage and Loss Assessment (DaLA) sektor permukiman periode November–Desember 2025 yang terdiri atas 1.613 observasi dari 15 kabupaten/kota dan 142 kecamatan. Model prediksi dibangun menggunakan Extreme Gradient Boosting (XGBoost), sedangkan interpretabilitas model dianalisis menggunakan SHapley Additive exPlanations (SHAP). Model divalidasi menggunakan 5-Fold Cross Validation, sedangkan evaluasi pada data pengujian dilakukan menggunakan Mean Absolute Error (MAE), Root Mean Square Error (RMSE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan rata-rata R² sebesar 0,7121 pada proses validasi silang, dengan MAE sebesar Rp5,87 miliar dan RMSE sebesar Rp34,28 miliar pada data pengujian. Analisis SHAP menunjukkan bahwa variabel Kerusakan, K3, Total Unit, serta beberapa variabel spasial pada tingkat kabupaten merupakan determinan utama kerugian pascabencana. Temuan ini menunjukkan bahwa pendekatan Explainable Machine Learning mampu mendukung penentuan prioritas rehabilitasi dan rekonstruksi pascabencana secara lebih transparan dan berbasis data.
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
B. Pradhan, S. Lee, A. Dikshit, and H. Kim, “Spatial flood susceptibility mapping using an explainable artificial intelligence (XAI) model,” Geoscience Frontiers, vol. 14, no. 6, Nov. 2023, doi: 10.1016/j.gsf.2023.101625.
H. Ren et al., “Flood Susceptibility Assessment with Random Sampling Strategy in Ensemble Learning (RF and XGBoost),” Remote Sens. (Basel)., vol. 16, no. 2, Jan. 2024, doi: 10.3390/rs16020320.
B. Choubin, A. Jaafari, J. Henareh, O. Karimi, and F. Sajedi Hosseini, “Explainable artificial intelligence (XAI) for interpreting predictive models and key variables in flood susceptibility,” Results in Engineering, vol. 27, Sep. 2025, doi: 10.1016/j.rineng.2025.105976.
B. D. Yuwono, L. M. Sabri, A. P. Wijaya, and M. Awaluddin, “Assessment of Flood Risk Induced by Land Subsidence Using Machine Learning,” Indonesian Journal of Geography, vol. 56, no. 3, pp. 376–386, 2024, doi: 10.22146/ijg.94726.
D. Khan, W. Akram, and S. Ullah, “Enhancing landslide susceptibility predictions with XGBoost and SHAP: a data-driven explainable AI method,” Geocarto Int., vol. 40, no. 1, 2025, doi: 10.1080/10106049.2025.2514725.
S. Darma et al., “Predictive Analysis of Flood Risk Factors Based on a Machine Learning Approach: Comparative Study of SVM and XGBoost Algorithms,” Journal of Technology and Computer (JOTECHCOM), vol. 3, no. 1, pp. 24–33, 2026.
N. Wang, H. Zhang, A. Dahal, W. Cheng, M. Zhao, and L. Lombardo, “On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values,” Geoscience Frontiers, vol. 15, no. 4, Jul. 2024, doi: 10.1016/j.gsf.2024.101800.
K. Nam, Y. Lee, S. Lee, S. Kim, and S. Zhang, “Explainable Artificial Intelligence (XAI) for Flood Susceptibility Assessment in Seoul: Leveraging Evolutionary and Bayesian AutoML Optimization,” Remote Sens. (Basel)., vol. 17, no. 13, Jul. 2025, doi: 10.3390/rs17132244.
J. Yang, D. Ahn, J. Bahk, S. Park, N. Rizqihandari, and M. Cha, “Assessing climate risks from satellite imagery with machine learning: A case study of flood risks in Jakarta,” Clim. Risk Manag., vol. 46, Jan. 2024, doi: 10.1016/j.crm.2024.100651.
C. Singha, V. K. Rana, Q. B. Pham, D. C. Nguyen, and E. Łupikasza, “Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment,” Environmental Science and Pollution Research, vol. 31, no. 35, pp. 48497–48522, Jul. 2024, doi: 10.1007/s11356-024-34286-7.
M. Waleed and M. Sajjad, “Advancing flood susceptibility prediction: A comparative assessment and scalability analysis of machine learning algorithms via artificial intelligence in high-risk regions of Pakistan,” J. Flood Risk Manag., vol. 18, no. 1, Mar. 2025, doi: 10.1111/jfr3.13047.
S. F. Dal Sasso, M. Rondinone, H. H. Aung, and V. Telesca, “An Explainable Machine Learning Framework for Flood Damage Mapping Using Remote Sensing and Ground-Based Data: Application to the Basilicata Ionian Coast (Italy),” Remote Sens. (Basel)., vol. 18, no. 8, Apr. 2026, doi: 10.3390/rs18081257.
S. Chehreh Chelgani, H. Nasiri, and M. Alidokht, “Interpretable modeling of metallurgical responses for an industrial coal column flotation circuit by XGBoost and SHAP-A ‘conscious-lab’ development,” Int. J. Min. Sci. Technol., vol. 31, no. 6, pp. 1135–1144, Nov. 2021, doi: 10.1016/j.ijmst.2021.10.006.
T. Chen et al., “T4SE-XGB: Interpretable Sequence-Based Prediction of Type IV Secreted Effectors Using eXtreme Gradient Boosting Algorithm,” Front. Microbiol., vol. 11, Sep. 2020, doi: 10.3389/fmicb.2020.580382.
G. Airlangga, “Performance Evaluation of Machine Learning Models for Predicting Household Energy Consumption: A Comparative Study,” Indonesian Journal of Artificial Intelligence and Data Mining, vol. 8, no. 1, p. 76, Dec. 2024, doi: 10.24014/ijaidm.v8i1.32791.
A. Riyanto, D. I. Putri, G. P. Artiani, and A. Khumaidi, “Hybrid Fuzzy-AHP and Machine Learning with Sensitivity Analysis for Urban Flood Risk Assessment,” JUSIFO (Jurnal Sistem Informasi), vol. 11, no. 2, pp. 141–152, Dec. 2025, doi: 10.19109/jusifo.v11i2.32227.
S. Mohammed et al., “The effects of data quality on machine learning performance on tabular data,” Inf. Syst., vol. 132, Jul. 2025, doi: 10.1016/j.is.2025.102549.
R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection.” [Online]. Available: http//roboticsStanfordedu/"ronnyk
J. Fang et al., “Application of multiple machine learning models to rainstorm disaster loss assessment and driving mechanism analysis in Zhejiang Province, China,” J. Hydrol. Reg. Stud., vol. 61, Oct. 2025, doi: 10.1016/j.ejrh.2025.102740.
J. Zheng, W. Fang, and J. Shao, “A novel framework for multi-hazard loss assessment of tropical cyclones: A county-level interpretable machine learning model,” International Journal of Disaster Risk Reduction, vol. 117, Feb. 2025, doi: 10.1016/j.ijdrr.2025.105204.
P. Marchanda Izzati and F. Fitriyani, “Implementasi Algoritma XGBoost Untuk Prediksi Capaian Bulanan Pendapatan Daerah Kota Bandung,” Jurnal CoSciTech (Computer Science and Information Technology), vol. 6, no. 2, pp. 104–111, Aug. 2025, doi: 10.37859/coscitech.v6i2.9578.
S. Sularno, W. Boy, P. Anggraini, A. Kamal, and F. Wang, “Data-driven Classification of Tsunami Evacuation Suitability Using XGBoost: A Case Study in Padang City,” International Journal of Intelligent Systems and Applications, vol. 18, no. 1, pp. 90–106, Feb. 2026, doi: 10.5815/ijisa.2026.01.07.
Batunacun, R. Wieland, T. Lakes, and C. Nendel, “Using Shapley additive explanations to interpret extreme gradient boosting predictions of grassland degradation in Xilingol, China,” Geosci. Model Dev., vol. 14, no. 3, pp. 1493–1510, Mar. 2021, doi: 10.5194/gmd-14-1493-2021.
A. P. Sari, Billy, D. A. Tsaqif, B. Sartono, and A. R. Firdawanti, “Classification of Drinking Water Source Suitability in West Java Using XGBoost and Cluster Analysis Based on SHAP Values,” Indonesian Journal of Statistics and Its Applications, vol. 8, no. 2, pp. 202–214, Dec. 2024, doi: 10.29244/ijsa.v8i2p202-214.
W. Wijiyanto, A. I. Pradana, S. Sopingi, and V. Atina, “Teknik K-Fold Cross Validation untuk Mengevaluasi Kinerja Mahasiswa,” Jurnal Algoritma, vol. 21, no. 1, May 2024, doi: 10.33364/algoritma/v.21-1.1618.
R. Anisa, B. Sartono, P. Silvianti, and A. Alamudi, “CONSTRUCTING EARTHQUAKE DISASTER-EXPOSURE LIKELIHOOD INDEX USING SHAPLEY-VALUE REGRESSION APPROACH *,” 2019.
S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” Nov. 2017, [Online]. Available: http://arxiv.org/abs/1705.07874
J. Zhao, C. Zhang, J. Wang, Z. Abbas, and Y. Zhao, “Machine learning and SHAP-based susceptibility assessment of storm flood in rapidly urbanizing areas: a case study of Shenzhen, China,” Geomatics, Natural Hazards and Risk, vol. 15, no. 1, 2024, doi: 10.1080/19475705.2024.2311889.
S. Li, X. Ge, G. Jin, Z. Lou, and H. Yang, “Flood dynamic monitoring and XGBoost-SHAP based risk assessment: A case study of the 23·7 extreme rainstorm in BTH region, China,” Environmental and Sustainability Indicators, vol. 28, Dec. 2025, doi: 10.1016/j.indic.2025.101020.
A. Tella, Q. B. Pham, I. Zahidi, C. M. Fai, and K. S. M. H. Ibrahim, “Advancing Flood Susceptibility Mapping with Explainable AI: A Novel Application of Accumulated Local Effects (ALE),” Water Resources Management, vol. 40, no. 4, Mar. 2026, doi: 10.1007/s11269-025-04430-0.
O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-56706-x.